© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108549
    Prev
    Next
    INDEX
    Explanations

    references to configuration settings and method interactions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ưá»
    -0.08
     Ston
    -0.06
     bench
    -0.06
    ãĤĿ
    -0.06
     targeted
    -0.06
    crollView
    -0.06
    à¹īาร
    -0.06
     targeting
    -0.06
     online
    -0.06
    Pragma
    -0.06
    POSITIVE LOGITS
    anship
    0.07
    ownership
    0.07
    åĤ
    0.07
     ctor
    0.06
    å±¥
    0.06
    имо
    0.06
     lá
    0.06
    WithMany
    0.06
     Weak
    0.06
     voy
    0.06
    Activations Density 0.003%

    No Known Activations